检索结果-内蒙古大学图书馆

GPT-4 enhanced multimodal grounding for autonomous driving:Leveraging cross-modal attention with large language models

引用

Communications in Transportation Research 2024年第1期4卷 5-23页

作者： Haicheng Liao Huanming Shen Zhenning Li Chengyue Wang Guofa Li Yiming Bie Chengzhong Xu State Key Laboratory of Internet of Things for Smart City and Department of Computer and Information Science University of MacaoMacao SAR999078China Department of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610000China State Key Laboratory of Internet of Things for Smart City and Departments of Civil and Environmental Engineering and Computer and Information Science University of MacaoMacao SAR999078China State Key Laboratory of Internet of Things for Smart City and Departments of Civil and Environmental Engineering University of MacaoMacao SAR999078China College of Mechanical and Vehicle Engineering Chongqing UniversityChongqing400030China School of Transportation Jilin UniversityChangchun130000China

In the field of autonomous vehicles(AVs),accurately discerning commander intent and executing linguistic commands within a visual context presents a significant *** paper introduces a sophisticated encoder-decoder framework,developed to address visual grounding in *** Context-Aware Visual Grounding(CAVG)model is an advanced system that integrates five core encoders—Text,Emotion,Image,Context,and Cross-Modal—with a multimodal *** integration enables the CAVG model to adeptly capture contextual semantics and to learn human emotional features,augmented by state-of-the-art Large Language Models(LLMs)including *** architecture of CAVG is reinforced by the implementation of multi-head cross-modal attention mechanisms and a Region-Specific Dynamic(RSD)layer for attention *** architectural design enables the model to efficiently process and interpret a range of cross-modal inputs,yielding a comprehensive understanding of the correlation between verbal commands and corresponding visual *** evaluations on the Talk2Car dataset,a real-world benchmark,demonstrate that CAVG establishes new standards in prediction accuracy and operational ***,the model exhibits exceptional performance even with limited training data,ranging from 50%to 75%of the full *** feature highlights its effectiveness and potential for deployment in practical AV ***,CAVG has shown remarkable robustness and adaptability in challenging scenarios,including long-text command interpretation,low-light conditions,ambiguous command contexts,inclement weather conditions,and densely populated urban environments.

关键词： Autonomous driving Visual grounding Cross-modal attention Large language models Human-machine interaction

来源：评论

学校读者我要写书评

暂无评论

Emergence, Evolution, and Applications of Cyber-Physical Systems in Smart Society 4

Emergence, Evolution, and Applications of Cyber-Physical Sys...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Kumar, Sunil Bhowmik, Biswajit National Institute of Technology Karnataka Maharshi Patanjali Cps Lab Brics Laboratory Department of Computer Science and Engineering Surathkal Mangalore575025 India

ISBN: (纸本)9798350343670

With rapid technological advancement, cyber-physical systems (CPS) become an emerging era of engineered systems based on computing, networking, and control technologies that revolutionize human lives. New and smart CPS drives innovation and competition in industrial automation, transportation, healthcare applications, etc. Therefore, it is essential to explore the area. The paper presents the emergence of CPS. It includes CPS's evolution, its necessity, and its importance. Then, we explore the diverse applications of CPS in a smart society. Next, we explore various challenges and recent state-of-the-art to overcome these challenges. CPS connects strongly to the currently prevalent terms Internet of Things, the Industrial Internet, Industry 4.0, and Internet of Everything. All of these illustrate a technology that fundamentally connects the physical and digital worlds. CPS is more foundational and durable than all of these. Thus, the work presented here provides a view of substantial social consequences, making its trend progressive. © 2024 IEEE.

关键词： CPS Application CPS Challenges and Research Dimensions CPS Classification CPS Emergence Cyber-Physical Systems

来源：评论

学校读者我要写书评

暂无评论

Movable Antenna-Aided Hybrid Beamforming for Multi-User Communications

引用

IEEE Transactions on Vehicular Technology 2025年第6期74卷 9899-9903页

作者： Zhang, Yichi Zhang, Yuchen Zhu, Lipeng Xiao, Sa Tang, Wanbin Eldar, Yonina C. Zhang, Rui University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China University of Electronic Science and Technology of China National Key Laboratory of Science and Technology on Communications Chengdu611731 China Kash Institute of Electronics and Information Industry Kash844000 China Weizmann Institute of Science Faculty of Mathematics and Computer Science Rehovot7610001 Israel National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore Chinese University of Hon g Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen518172 China

In this correspondence, we propose a movable antenna (MA)-aided multi-user hybrid beamforming scheme with a sub-connected structure, where multiple movable sub-arrays can independently change their positions within different local regions. To maximize the system sum rate, we jointly optimize the digital beamformer, analog beamformer, and positions of sub-arrays, under the constraints of unit modulus, finite movable regions, and power budget. Due to the non-concave/non-convex objective function/constraints, as well as the highly coupled variables, the formulated problem is challenging to solve. By employing fractional programming, we develop an alternating optimization framework to solve the problem via a combination of Lagrange multipliers, penalty method, and gradient descent. Numerical results reveal that the proposed MA-aided hybrid beamforming scheme significantly improves the sum rate compared to its fixed-position antenna (FPA) counterpart. Moreover, with sufficiently large movable regions, the proposed scheme with sub-connected MA arrays even outperforms the fully-connected FPA array. © 1967-2012 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Optimizing Lender Portfolios: A P2P Lending Recommendation Approach 4

Optimizing Lender Portfolios: A P2P Lending Recommendation A...

引用

4th IEEE Asian Conference on Innovation in Technology, ASIANCON 2024

作者： Sannapareddy, Varshini Rifah, Umais Anusha Hegde, H. Bhowmik, Biswajit National Institute of Technology Karnataka Ishwarchandra Vidyasagar Ait Lab Brics Laboratory Department of Computer Science and Engineering Surathkal Mangalore575025 India

ISBN: (纸本)9798350354218

The proliferation of peer-to-peer (P2P) lending platforms has ushered in a new era of financial accessibility, but it has also brought to the forefront the growing concern of loan defaults. This paper explores the increasing significance of P2P lending platforms and addresses the critical issue of loan default prediction. The study focuses on the application of machine learning techniques, specifically employing the Random Forest algorithm and logistic regression, to train a predictive model for assessing the likelihood of default within a loan portfolio. The primary objective is to enhance the decision-making process for lenders by recommending optimal loan portfolios based on the predictive insights generated by the model. By leveraging the capabilities of this robust algorithm, the research aims to contribute to the advancement of risk assessment methodologies in P2P lending, ultimately fostering more informed and secure lending practices on these platforms. We trained and compared logistic Reression and random forest models and derived resultant optimal portfolio by considering both the models which is intended to give better results than a single model. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Enhancing Financial Accessibility: A Tailored UPI Payment Application for Divyangjan 10

Enhancing Financial Accessibility: A Tailored UPI Payment Ap...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Bhowmik, Biswajit Sudhama, Kruthika K. Dongala, Joshitha R. Antony, Reshma T. Girish, K.K. National Institute of Technology Karnataka Maharshi Sushrut Cas Lab Brics Laboratory Department of Computer Science and Engineering Mangalore Surathkal575025 India

ISBN: (纸本)9798350384369

The emergence of financial technology (FinTech) has transformed the financial sector, introducing a new era characterized by state-of-the-art technologies that enhance speed, affordability, and accessibility. The proliferation of the internet and smartphones has further accelerated this transformation, fostering greater connectivity and global interaction. Subsequently, these advancements have significantly expanded financial inclusion, ensuring access to financial services for previously under-served populations. While the rise of FinTech has propelled financial inclusion for many, individuals with disabilities have not experienced commensurate improvements in their financial accessibility. As the banking sector increasingly migrates to online platforms, people with disabilities encounter barriers stemming from inaccessible websites, mobile applications, and online banking services. This paper introduces a specialized UPI payment application designed explicitly for individuals with disabilities. The objective is to integrate this underserved demographic into the digital financial landscape, fostering financial inclusion and enhancing access to essential financial services. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

ANUBIS: Hybrid FPAA-FPGA Architecture for Entropy-Based True Random Number Generation in Secure UAV Communication

引用

IEEE Embedded Systems Letters 2024年第3期17卷 164-167页

作者： El-Hadedy, Mohamed Abelian, Andrea Lee, Kenny Cheng, Benny Hwu, Wen-Mei California State Polytechnic University Department of Electrical and Computer Engineering Pomona United States University of Illinois at Urbana-Champaign Coordinated Science Laboratory United States Naval Surface Warfare Center United States

Field-Programmable Gate Arrays (FPGAs) and Field-Programmable Analog Arrays (FPAAs) are reconfigurable circuits that enable flexible digital and analog implementations post-manufacturing. FPGAs are widely used in telecommunications, mixed-signal, and embedded systems due to their parallel processing and reconfigurability. Meanwhile, FPAAs provide flexibility for analog systems, which is crucial for modern mixed-signal processing. This study introduces ANUBIS, a hybrid system combining FPGA and FPAA technologies to generate true random numbers (TRNGs) for secure UAV communication. Due to its reliability and cost efficiency, ANUBIS leverages a thermistor circuit as an entropy source. The FPAA amplifies the analog noise generated by the thermistor, while the FPGA digitizes and processes the signal using Von Neumann Whitening (VNW) to remove bias. The ASCON hash function is applied to the whitened bitstream to generate cryptographically secure keys. These keys are utilized in a DHKE to enable secure communication via Bluetooth Low Energy (BLE), an ideal protocol for energy-constrained UAV applications. ANUBIS demonstrates reconfigurability, power efficiency, and ease of implementation, showcasing its potential for secure communication applications. It achieves robust randomization, setting a new standard for UAV communication security and addressing applications requiring reliable TRNG solutions. The system consumes 1.615 W in total, with 1.54 W consumed by the FPGA and 75 mW by the FPAA. Resource utilization on the PYNQ-Z1 board includes 5,186 LUTs (9.75%), 549 units of memory (3.15%), and 5.5 units of BRAM (3.93%), indicating moderate resource usage with room for future enhancements. By integrating reliable analog noise harvesting with efficient digital post-processing, ANUBIS offers a novel approach to TRNG design, demonstrating the potential for broader cryptographic applications in resource-constrained environments. © 2009-2012 IEEE.

关键词： Random number generation

来源：评论

学校读者我要写书评

暂无评论

Surrogate-Assisted Multiobjective Neural Architecture Search for Real-Time Semantic Segmentation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第6期4卷 1602-1615页

作者： Lu, Zhichao Cheng, Ran Huang, Shihua Zhang, Haoming Qiu, Changxiao Yang, Fan Southern University of Science and Technology Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China Huawei Technologies Co. Ltd. Hisilicon Research Department Shenzhen518055 China

The architectural advancements in deep neural networks have led to remarkable leap-forwards across a broad array of computer vision tasks. Instead of relying on human expertise, neural architecture search (NAS) has emerged as a promising avenue toward automating the design of architectures. While recent achievements on image classification have suggested opportunities, the promises of NAS have yet to be thoroughly assessed on more challenging tasks of semantic segmentation. The main challenges of applying NAS to semantic segmentation arise from two aspects: 1) high-resolution images to be processed;2) additional requirement of real-time inference speed (i.e., real-time semantic segmentation) for applications such as autonomous driving. To meet such challenges, we propose a surrogate-assisted multiobjective method in this article. Through a series of customized prediction models, our method effectively transforms the original NAS task to an ordinary multiobjective optimization problem. Followed by a hierarchical prescreening criterion for in-fill selection, our method progressively achieves a set of efficient architectures trading-off between segmentation accuracy and inference speed. Empirical evaluations on three benchmark datasets together with an application using Huawei Atlas 200 DK suggest that our method can identify architectures significantly outperforming existing state-of-the-art architectures designed both manually by human experts and automatically by other NAS methods. Code is available from here. © 2020 IEEE.

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

Multi-Classification Segmentation Method of Gastric Cancer Pathological Images Based on Deep Learning

Multi-Classification Segmentation Method of Gastric Cancer P...

引用

2024 lEEE International Conference on Advanced Information, Mechanical Engineering, Robotics and Automation, AIMERA 2024

作者： Zhou, Hehu Pan, Jingshan Na, Li Ding, Qingyan Zhou, Chengjun Du, Wantong Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China The Second Hospital of Shandong University Department of Pathology Jinan China

ISBN: (纸本)9798350343335

Gastric cancer is a serious health threat, and pathological imaging is important in detecting it. These images can assist doctors in accurately determining the location of the cancer, thereby providing an important reference for clinical decision-making. In the field of image processing, deep learning technology is leading to more and more excellent segmentation models. The Trans-Unet model has achieved success in the image segmentation. However, when applying this model to gastric cancer pathological section data, the segmentation boundary appears jagged. We propose three possible solutions. First, we designed an attention connection module to replace the skip connections in the model to enhance the prediction accuracy of the model. Second, we designed a prediction processing unit that takes the model's prediction results as input and uses a Conditional Random Field (CRF) for further prediction calculations. To enable the model to meet the requirements of multi-classification of images, we designed a dynamic weight selection module to enhance the model's accuracy for multi-classification tasks. After our optimization, the optimized model improved by 8% on the DSC evaluation index and 39% on the HD evaluation index. In addition, the jagged boundary problem in the prediction results has also been effectively improved. Through comparative experiments and erosion experiments, we found that the improved method enhances the accuracy of model prediction and reduces the jagged results at the boundary. © 2024 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Information Security Evaluation by Information Flow Analysis Based on Stochastic Petri Nets

Information Security Evaluation by Information Flow Analysis...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Tu, Hanqian Xiang, Dongming Lin, Wang Liu, Guanjun Zhejiang Sci-Tech University Department of Computer Science and Technology Hangzhou310018 China Shanghai Electronic Transactions and Information Service Collaborative Innovation Center Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Department of Computer Science Shanghai201804 China

ISBN: (纸本)9781665410205

The Petri-net-based information flow analysis offers an effective approach for detecting information leakage by the concept of non-interference. Although the related studies propose efficient solutions, they lack quantitative evaluation on information leakage. In this paper, we propose a novel method for quantitative evaluation of information security based on stochastic labeled Petri nets (SLPNs) and information flow analysis. Specifically, we introduce four different levels of security metrics, and provide a methodology for evaluating the information security. Furthermore, a case study is presented to show the feasibility of our method. © 2024 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Sparse Color Fourier Ptychographic Microscopy With Implicit Neural Representations

Sparse Color Fourier Ptychographic Microscopy With Implicit ...

引用

Computational Optical Sensing and Imaging, COSI 2024 - Part of Optica Imaging Congress

作者： Chan, Matthew A. Zhou, Haowen Feng, Brandon Y. Metzler, Christopher A. Department of Computer Science University of Maryland College ParkMD20742 United States Department of Electrical Engineering California Institute of Technology PasadenaCA91125 United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States

We apply implicit neural representations—which naturally capture spectral regularity—to reconstruct color Fourier ptychographic microscopy images from spectrally-sparse measurements. We conduct experiments on real-world specimens and demonstrate reconstruction quality comparable with fully sampled methods. © 2024 The Author(s).

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：